INDEX

Explanations

club

np_max-act · gemini-2.0-flash

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

URT

-0.29

ns

-0.28

 selv

-0.27

 bulk

-0.27

æ¯Ķä¾ĭ

-0.27

esty

-0.25

Bulk

-0.25

 bang

-0.25

Ĥ¬

-0.24

 Bulk

-0.24

POSITIVE LOGITS

æīĵå¾Ĺ

0.27

alten

0.25

 ÅĽro

0.24

 todd

0.24

à¸Ħà¸¡

0.24

Parameters

0.24

arrings

0.23

ä¸ºä»Ģä¹Īè¦ģ

0.23

Design

0.23

æıĲä¾Ľ

0.23

Activations Density 0.039%

club

No Comments

No Known Activations