INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

anca

-0.26

éĢł

-0.26

enario

-0.25

.Raw

-0.25

Shield

-0.25

ÙĬØ«

-0.24

åĬłéĩį

-0.24

enarios

-0.23

ARIANT

-0.23

ç¥ī

-0.23

POSITIVE LOGITS

 domination

0.26

textField

0.25

 Hubb

0.24

Po

0.24

èµ·

0.24

.gradient

0.24

gy

0.24

 ActionController

0.24

æĨĳ

0.23

licity

0.23

Activations Density 0.019%

No Known Activations

This feature has no known activations.