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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sadd

-0.27

å½ĵå¹´

-0.27

è¶³

-0.26

æĬĵæįķ

-0.25

ulan

-0.25

Collapsed

-0.25

 firefight

-0.25

collapsed

-0.25

è®Ńç»ĥ

-0.24

è¨ĵç·´

-0.24

POSITIVE LOGITS

kÃ¼

0.30

kin

0.27

 aspir

0.26

quirer

0.25

ernes

0.24

éĹª

0.23

/GPL

0.23

çħ¨

0.23

ibold

0.23

utory

0.23

Activations Density 0.338%

No Known Activations

This feature has no known activations.