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

cul

-0.25

ÐĪ

-0.24

 organism

-0.24

iless

-0.24

Lo

-0.23

Sig

-0.23

æ¯į

-0.23

 creature

-0.23

tor

-0.23

Mother

-0.23

POSITIVE LOGITS

 urlparse

0.25

ä¸Ĭæ±½

0.25

.sap

0.25

æ³Į

0.24

iment

0.24

iments

0.24

çł§

0.24

()?.

0.24

æĬķ

0.24

LV

0.23

Activations Density 0.095%

No Known Activations

This feature has no known activations.