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

\db

-0.27

datable

-0.26

utan

-0.25

éĦ£

-0.24

_PLATFORM

-0.23

 demi

-0.23

éŁ³åĵį

-0.23

ç¥

-0.23

shine

-0.23

éģ¥

-0.23

POSITIVE LOGITS

 Entr

0.30

 PIPE

0.27

 EspaÃ±ol

0.26

å¸ģ

0.25

 centroids

0.24

rett

0.24

èµ°è¿ĩ

0.24

CAB

0.24

qua

0.23

 centroid

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.