INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CAD

-0.28

Ä°Z

-0.25

(an

-0.24

 Prosecutor

-0.24

èĻ¾

-0.24

çĭ¬

-0.24

åĬ¡

-0.23

iaux

-0.23

Catch

-0.23

ÙĬÙħØ©

-0.23

POSITIVE LOGITS

ogan

0.27

parity

0.26

 Goldberg

0.26

 parity

0.26

å¤·

0.25

æĽĻ

0.25

hatt

0.24

ç²²

0.24

----------------------------------------------------------------------↵

0.24

çļĦåħ´è¶£

0.24

Activations Density 0.009%

No Known Activations

This feature has no known activations.