INDEX

Explanations

attributed/credited

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

worth

-0.30

é¡¿

-0.27

éĿ

-0.26

Ton

-0.25

POR

-0.24

æľīä¸Ģå®ļ

-0.24

Ton

-0.24

"[

-0.24

æĬķ

-0.24

LAT

-0.23

POSITIVE LOGITS

\/\/

0.29

udem

0.28

Difficulty

0.28

 difficulty

0.27

 Difficulty

0.27

_life

0.27

/up

0.25

ixmap

0.24

usage

0.24

-life

0.24

Activations Density 0.017%

attributed/credited

No Comments

No Known Activations