INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Carp

-0.28

outs

-0.27

ä¾Ŀçħ§

-0.24

ä»Ģä¹Īéĥ½

-0.24

åĽłä¸ºä»ĸä»¬

-0.24

ä¸įæŃ»

-0.24

omit

-0.24

åħ¬åħ±åľºæīĢ

-0.24

Stories

-0.24

è§Ĵåº¦çľĭ

-0.24

POSITIVE LOGITS

accessible

0.26

.tex

0.26

fad

0.26

nd

0.25

orean

0.25

äººæīįåŁ¹åħ»

0.25

ì½©

0.24

-con

0.24

ä¹ĲéĺŁ

0.24

nd

0.24

Activations Density 39.784%

No Known Activations

This feature has no known activations.