INDEX

Explanations

-gl

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

 Subway

-0.28

çķ¥æľī

-0.28

 defaultProps

-0.26

itta

-0.25

branches

-0.24

 headlines

-0.24

 branches

-0.24

æĤŃ

-0.24

 holds

-0.23

 Branch

-0.23

POSITIVE LOGITS

éģĵçĲĨ

0.30

Cle

0.26

æĤ²åĵĢ

0.25

éĤ£å¤©

0.25

åŁİä¹¡

0.25

çļĦéģĵçĲĨ

0.25

çĶ·æĢ§

0.24

åį³ä¾¿æĺ¯

0.24

 heterosexual

0.24

elters

0.24

Activations Density 0.015%

-gl

No Comments

No Known Activations