INDEX

Explanations

spice

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

æŀľ

-0.34

åºıåĪĹ

-0.28

çĶµ

-0.27

éĢĬ

-0.27

 Mais

-0.26

 beau

-0.26

ahkan

-0.26

è®ºåĿĽ

-0.25

éĺ³

-0.25

å¹¿çĶµ

-0.24

POSITIVE LOGITS

[__

0.28

distributed

0.26

 differentiated

0.26

 distributed

0.26

 accompany

0.25

 persisted

0.24

inine

0.24

ARB

0.24

ä¸¤æ¬¾

0.24

.intent

0.24

Activations Density 0.302%

spice

No Comments

No Known Activations