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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alty

-0.27

.bb

-0.26

CRY

-0.25

SELL

-0.25

Joe

-0.25

stral

-0.25

çŃīåľ°

-0.24

çľĭä»ĸ

-0.24

istrict

-0.24

OTA

-0.24

POSITIVE LOGITS

ductive

0.26

ulus

0.26

 indu

0.25

edis

0.25

[/

0.25

riculum

0.25

laden

0.24

 Dexter

0.24

ä¹ĺ

0.24

asmus

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.