INDEX

Explanations

Prefixes and suffixes

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

 Marco

-0.28

/jav

-0.28

çļĦä¸Ģç§į

-0.26

cheid

-0.26

åıĤèĢĥ

-0.26

voy

-0.26

 “âĢ¦

-0.26

à¹Īà¸ĩ

-0.25

âį

-0.25

 Franco

-0.25

POSITIVE LOGITS

çĪ±å¥½

0.27

éľĩèį¡

0.26

bind

0.26

-dot

0.25

 bless

0.25

å°ıåŃĲ

0.25

å®Įå¥½

0.24

çĪ°

0.24

 bind

0.24

ãĤĪãģĭãģ£ãģŁ

0.24

Activations Density 0.036%

Prefixes and suffixes

No Comments

No Known Activations