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

è¾Ļ

-0.27

haft

-0.26

avor

-0.25

ãĤ·ãĥ£ãĥ«

-0.24

astes

-0.24

(LP

-0.24

èĢĮå¯¹äºİ

-0.24

infer

-0.24

ãĥªãĥ¼

-0.24

hort

-0.23

POSITIVE LOGITS

ç±

0.26

è¯´æĺİ

0.26

äº

0.25

çĽĳçĿ£

0.24

ilit

0.24

åĴĮåľ°åĮº

0.24

Protection

0.24

sup

0.24

npm

0.24

iture

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.