INDEX

Explanations

There

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

.scheme

-0.29

xDC

-0.27

.Scheme

-0.25

æ¸¡

-0.25

è®¯

-0.25

INTR

-0.25

ħ§

-0.24

å·¨äºº

-0.24

 prescribing

-0.24

edReader

-0.23

POSITIVE LOGITS

regon

0.32

 ÐµÑīÑĳ

0.27

æĹ¥åīį

0.27

ä¸¤å¤©

0.27

StateException

0.26

ä¸¤æ¬¾

0.26

æĻ¨æĬ¥

0.26

sonian

0.25

perate

0.25

åħ¨æĿĳ

0.24

Activations Density 0.016%

There

No Comments

No Known Activations