INDEX

Explanations

worse

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

inium

-0.28

æĦŁåĬ¨

-0.27

inton

-0.27

 speech

-0.26

æĸ°ä¸ĸçºª

-0.25

 Suite

-0.25

cot

-0.24

æ··æ²Į

-0.24

 zost

-0.24

pty

-0.24

POSITIVE LOGITS

 Hubbard

0.29

çľī

0.29

amo

0.25

åµĭ

0.24

 Wander

0.24

WindowSize

0.24

<article

0.24

URE

0.24

 Hats

0.24

 curtains

0.23

Activations Density 0.324%

worse

No Comments

No Known Activations