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

 Approx

-0.24

éĺŁ

-0.23

Equ

-0.23

onden

-0.23

éģĵ

-0.23

è¾Ĺ

-0.23

ocache

-0.23

roring

-0.22

idores

-0.22

 Depart

-0.22

POSITIVE LOGITS

pit

0.29

anche

0.27

_cast

0.25

let

0.25

LET

0.25

Hung

0.25

cast

0.25

application

0.24

vel

0.24

ä¸ľæĸ¹

0.24

Activations Density 0.016%

No Known Activations

This feature has no known activations.