INDEX

Explanations

code libraries and documentation

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

Lod

-0.27

 smarter

-0.27

(validate

-0.26

èį·èĬ±

-0.25

 reflections

-0.25

-enable

-0.25

æĻºæħ§

-0.25

å¤®

-0.24

æĻºæħ§åŁİå¸Ĥ

-0.24

åı²ä¸ĬæľĢ

-0.23

POSITIVE LOGITS

oken

0.27

 Keynes

0.25

kv

0.25

æĺĨ

0.25

 Allied

0.25

åħµ

0.25

ife

0.24

åľ¨çİ°åľº

0.24

è¿Ľå±ķ

0.24

aden

0.24

Activations Density 0.003%

code libraries and documentation

No Comments

No Known Activations