INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 egret

-0.29

gos

-0.26

çļĦé¢ľèī²

-0.26

 negativity

-0.25

NEG

-0.25

peak

-0.25

_LA

-0.25

è¾ľè´Ł

-0.24

çļĦèº«å½±

-0.24

é¢ľåĢ¼

-0.24

POSITIVE LOGITS

 collaborators

0.27

acons

0.26

 sympath

0.26

 exactly

0.26

 breath

0.24

 Holt

0.24

.camel

0.24

 collabor

0.23

 circum

0.23

 members

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.