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

.Absolute

-0.27

 strictly

-0.27

 Constit

-0.26

å¦«

-0.26

amen

-0.25

CTYPE

-0.25

 constit

-0.24

 HOLDER

-0.24

toy

-0.24

AuthProvider

-0.24

POSITIVE LOGITS

çħ

0.30

town

0.26

 Knight

0.26

æģĥ

0.26

è®½

0.26

 Webb

0.25

ios

0.25

hill

0.25

å½ĵæĹ¥

0.25

 Cooper

0.25

Activations Density 0.001%

No Known Activations

This feature has no known activations.