INDEX

Explanations

areas

np_max-act · gemini-2.0-flash

references to geographic or administrative areas, especially protected or conservation designations.

oai_token-act-pair · gpt-5 Triggered by @liuliujiujiu05

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.setItem

-0.27

void

-0.26

 enforced

-0.26

 negÃ³cio

-0.26

ichert

-0.25

enko

-0.25

æĹı

-0.24

imenti

-0.24

 barang

-0.24

 Estates

-0.24

POSITIVE LOGITS

 rall

0.31

èµĮ

0.27

[length

0.27

loser

0.26

è¿ĻäºĽäºº

0.25

TRACK

0.25

ä¸ĢæĹ¦

0.25

ä¹Łæĺ¯å¦ĤæŃ¤

0.24

è¿Ļä¹Łæĺ¯

0.24

 vamp

0.24

Activations Density 0.127%

areas

references to geographic or administrative areas, especially protected or conservation designations.

No Comments

No Known Activations