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

æįº

-0.28

(conv

-0.27

MIT

-0.26

å¿ĹæĦ¿

-0.26

 inval

-0.26

ãĤĥ

-0.26

IRA

-0.25

ä¸įæ¸ħ

-0.25

 Cous

-0.25

(Conv

-0.25

POSITIVE LOGITS

 accesses

0.26

æ³·

0.25

ÑĥÐ³

0.24

isl

0.24

å®¾é¦Ĩ

0.23

hsi

0.23

acman

0.23

ç®ª

0.23

ãĥĳãĤ¹

0.23

meer

0.22

Activations Density 1.365%

No Known Activations

This feature has no known activations.