INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alu

-0.28

(Bundle

-0.27

idge

-0.26

æľ¬ä¹¦

-0.24

isle

-0.24

POSITE

-0.24

 Shaun

-0.24

 casc

-0.23

WithMany

-0.23

æľ¬æĽ¸

-0.23

POSITIVE LOGITS

historic

0.31

UCT

0.28

icts

0.28

uct

0.26

 historic

0.26

 reconnaissance

0.25

::-

0.25

ertools

0.25

/MIT

0.25

ict

0.24

Activations Density 0.070%

No Known Activations

This feature has no known activations.