INDEX

Explanations

No Explanations Found

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 choke

-0.29

 guess

-0.28

åĪĩå°Ķ

-0.27

ota

-0.27

 guessing

-0.26

 hÆ¡i

-0.25

æīĭèĦļ

-0.25

licit

-0.25

ograd

-0.24

ayas

-0.24

POSITIVE LOGITS

æįŁ

0.29

ç®Ķ

0.27

iens

0.26

é©¹

0.25

è¯įæĿ¡

0.25

binding

0.24

hei

0.24

ENTS

0.24

itory

0.23

rovers

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.